Borrowing it
Nothing to install: this file belongs to 0xNyk/unmachined. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/0xNyk/unmachined/main/AGENTS.mdgit clone --depth 1 https://github.com/0xNyk/unmachinedWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/0xnyk/unmachined/agents-md)<a href="https://agentmods.dev/instructions/0xnyk/unmachined/agents-md"><img src="https://agentmods.dev/badge/instructions/0xnyk/unmachined/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/0xnyk/unmachined/agents-md"><img src="https://agentmods.dev/badge/instructions/0xnyk/unmachined/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00606 | $0.00606 |
| Opus 5 | $0.00303 | $0.00303 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
unmachined AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent operating rules
These rules apply to every coding agent working in this repository.
Scope
- Read
SKILL.mdbefore changing skill behavior. - Preserve user changes and unrelated working-tree edits.
- Keep the root
SKILL.mdfocused on routing. Put detailed rules inreferences/and deterministic checks inscripts/. - Maintain Python 3.8 compatibility and zero runtime dependencies.
- Always-on policy lives in
references/always-on.mdplusscripts/config_lib.py/scripts/onboard.py. Do not scatter config paths. - When editing this skill's own docs, keep unmachined text rules (no em-dashes as decoration in new prose; concrete findings).
Verification
Before presenting a change as complete:
python3 scripts/validate_skill.py
python3 scripts/scan_text.py README.md
python3 scripts/scan_text.py SKILL.md
git diff --check
Run python3 scripts/scan_ui.py <path> when changing UI examples or frontend
rules. Never claim a check, render, or test passed unless it ran successfully.
Git contract
- Inspection commands such as
git status,git diff, andgit logare always allowed. - Work on a topic branch named
agent/<short-task>unless the user explicitly requests another branch or the host provides an isolated worktree. - Stage only files or hunks belonging to the current task. Use
git add -pwhen a touched file also contains unrelated edits. - Review
git diff --cachedand rungit diff --cached --checkbefore every commit. - Commits must be cohesive, verified, and described by a short imperative
message. Do not use
git commit -aor stage the whole repository by default. - Commit only when the user asks, or when the task explicitly includes creating a commit. Pushing, opening a pull request, merging, tagging, releasing, and posting external comments always require explicit user authorization.
- Push only the current topic branch. Never push directly to
mainunless the user explicitly requests it and repository policy permits it. - Never amend, rebase, reset, delete branches, or force-push without a specific
request. If a force-push is unavoidable, explain why and use
--force-with-lease; plain--forceis prohibited. - After committing or pushing, report the branch, commit SHA, checks run, and any remaining local changes.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 61 lines · 606 tokens per session scan A 9ee33689948b
unmachined AGENTS.md is an instructions file published in the GitHub repository 0xNyk/unmachined (10 stars, last pushed 14d ago), licensed MIT. It adds 606 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.